[FlashMLA] Update FlashMLA to expose new arguments (#32810)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
This commit is contained in:
Lucas Wilkinson
2026-01-21 22:02:39 -07:00
committed by GitHub
parent 49d9653852
commit 889722f3bf
8 changed files with 132 additions and 216 deletions

3
.gitignore vendored
View File

@@ -7,6 +7,9 @@ vllm/vllm_flash_attn/*
# OpenAI triton kernels copied from source
vllm/third_party/triton_kernels/*
# FlashMLA interface copied from source
vllm/third_party/flashmla/flash_mla_interface.py
# triton jit
.triton